Datasets › SWAG

SWAG (Situations With Adversarial Generations)

Introduced by Rowan Zellers et al. in SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference16 Aug 2018 archive 2025-07-28

Given a partial description like "she opened the hood of the car," humans can reason about the situation and anticipate what might come next ("then, she examined the engine"). SWAG (Situations With Adversarial Generations) is a large-scale dataset for this task of grounded commonsense inference, unifying natural language inference and physically grounded reasoning.

The dataset consists of 113k multiple choice questions about grounded situations. Each question is a video caption from LSMDC or ActivityNet Captions, with four answer choices about what might happen next in the scene. The correct answer is the (real) video caption for the next event in the video; the three incorrect answers are adversarially generated and human verified, so as to fool machines but not humans. The authors aim for SWAG to be a benchmark for evaluating grounded commonsense NLI and for learning representations.

Source: SWAG Image Source: Zellers et al

Benchmarks archive 2025-07-28

All 2 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.

Syntology 1 newer paper was judged to report on this dataset's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): Common Sense Reasoning · SWAG (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).

First row (archive order)PaperCode
Common Sense Reasoning SWAG DeBERTalarge Test 90.8 DeBERTa: Decoding-enhanced BERT with Disentangled Attention huggingface/transformers +13 5 Compare
Question Answering SWAG DeBERTaV3large Accuracy 93.4 DeBERTaV3: Improving DeBERTa using ELECTRA-Style... microsoft/DeBERTa +2 1 Compare

Papers archive 2025-07-28

papers with a benchmark row: 5 · with a code link: 4 · where Syntology ran a sample: 4 (4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all papers with a benchmark rowonly where code ran (4 of 5 with a benchmark row: 4 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 5 of 5 with a leaderboard row on this dataset's benchmarks, newest first by the archive's date (ties by slug; undated papers last).

The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset, not that list; the archive's count for this dataset is 163. The Syntology column is from Syntology's graph, stated per sample; it is not part of any archive number. A line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified” (C is a part of N, never taken away from it); the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. When the archive marks a repository official for the paper, the cell starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record.

PaperCodeResultsDateSamples run Syntology
DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing 3 1 18 Nov 2021 official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified
DeBERTa: Decoding-enhanced BERT with Disentangled Attention 14 1 5 Jun 2020 official: no sample here; runs from other or unrecorded repositories · 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified (3 pointer-only for licence)
RoBERTa: A Robustly Optimized BERT Pretraining Approach 67 1 26 Jul 2019 community repositories only · 37 ran (of which 11 constructed an object rather than computing a result; 36 with no instrument failure: 2 honoured, 0 violated, 34 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified (24 pointer-only for licence)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding 534 1 11 Oct 2018 official: no sample here; runs from other or unrecorded repositories · 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified (164 pointer-only for licence)
SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference 0 2 16 Aug 2018 not harvested

Dataset loaders archive 2025-07-28

4 loaders as listed in the archive; links are outbound and not re-checked here.

Tasks archive 2025-07-28

License archive 2025-07-28

MIT

Modalities archive 2025-07-28

Languages archive 2025-07-28

Variants archive 2025-07-28

  • SWAG

1 variant name, as the archive lists them.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections